bisectgroup/BiCA-base
Partial fine-tune vs thenlper/gte-base. Partial change: 78% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 24/48, Attention 84/96, other 48/50
Partial fine-tune vs thenlper/gte-base. Partial change: 78% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 3/5, Norms 24/48, Attention 84/96, other 48/50